# Qwen Image 2.0 API

Complete API reference for Qwen Image 2.0 models powered by Alibaba Qwen.

## Model Variants

This API supports four model variants:

| Model | ID | Description |
|-------|-----|-------------|
| **Qwen Image 2** | `qwen-image-2.0` | Text-to-image generation |
| **Qwen Image 2 Edit** | `qwen-image-2.0-edit` | Image editing and multi-image composition |
| **Qwen Image 2 Pro** | `qwen-image-2.0-pro` | Enhanced text-to-image generation with higher quality output |
| **Qwen Image 2 Pro Edit** | `qwen-image-2.0-pro-edit` | Enhanced image editing and multi-image composition |

## Quick Comparison

| Feature | Standard | Pro |
|---------|----------|-----|
| Text-to-Image | ✅ Yes | ✅ Yes |
| Image Editing | ✅ Yes | ✅ Yes |
| Aspect Ratios | 7 options | 7 options |
| Image Input (Edit) | ✅ Yes (1-6 images) | ✅ Yes (1-6 images) |
| Multi-Image Support | ✅ Yes | ✅ Yes |
| Output Quality | Standard | Enhanced |

| Feature | Text-to-Image | Edit |
|---------|---------------|------|
| Input | Text prompt | Image(s) + Text prompt |
| Image Input | ❌ No | ✅ Yes (1-6 images) |
| Multi-Image Support | ❌ No | ✅ Yes |
| Seed Support | ✅ Optional | ✅ Optional |

### Supported Aspect Ratios

Both Standard and Pro models support 7 aspect ratios:
- `16:9` (default), `9:16`, `1:1`, `4:3`, `3:4`, `3:2`, `2:3`

## Qwen Image 2 (Text-to-Image)

### Endpoint

```
POST /api/v1/image/task
```

### Authentication

```
Authorization: Bearer YOUR_API_KEY
```

### Request Parameters

#### Required

| Parameter | Type | Description |
|-----------|------|-------------|
| `model_name` | string | Must be `"qwen-image-2.0"` |
| `prompt` | string | Image generation prompt |
| `width` | number | Width ratio value (e.g., 16 for 16:9) |
| `height` | number | Height ratio value (e.g., 9 for 16:9) |

**Note:** The width:height ratio must be one of: `16:9`, `9:16`, `1:1`, `4:3`, `3:4`, `3:2`, `2:3`

#### Optional

| Parameter | Type | Description |
|-----------|------|-------------|
| `seed` | number | Random seed for reproducible results |

### Example Request

```javascript
const response = await fetch('https://api.flaq.ai/api/v1/image/task', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model_name: 'qwen-image-2.0',
    prompt: 'A serene mountain landscape at sunset',
    width: 16,
    height: 9
  })
});

const { data } = await response.json();
const taskId = data.task_id;

// Poll for results
const pollResponse = await fetch(
  `https://api.flaq.ai/api/v1/image/${taskId}`,
  {
    headers: { 'Authorization': 'Bearer YOUR_API_KEY' }
  }
);

const result = await pollResponse.json();
console.log(result.data.task_result.images[0].url);
```

## Qwen Image 2 Edit (Image Editing)

### Endpoint

```
POST /api/v1/image/task
```

### Request Parameters

#### Required

| Parameter | Type | Description |
|-----------|------|-------------|
| `model_name` | string | Must be `"qwen-image-2.0-edit"` |
| `prompt` | string | Description of desired edits |
| `width` | number | Width ratio value (e.g., 16 for 16:9) |
| `height` | number | Height ratio value (e.g., 9 for 16:9) |
| `image_url_list` | string[] | Array of input image URLs (1-6 items) |

**Note:** The width:height ratio must be one of: `16:9`, `9:16`, `1:1`, `4:3`, `3:4`, `3:2`, `2:3`

#### Optional

| Parameter | Type | Description |
|-----------|------|-------------|
| `seed` | number | Random seed for reproducible results |

### Single Image Edit Example

```javascript
{
  model_name: 'qwen-image-2.0-edit',
  prompt: 'Change the sky to sunset colors',
  width: 16,
  height: 9,
  image_url_list: ['https://example.com/image.jpg']
}
```

### Multi-Image Composition Example

Up to 6 images can be combined in a single request:

```javascript
{
  model_name: 'qwen-image-2.0-edit',
  prompt: 'Combine these images into a cohesive landscape',
  width: 16,
  height: 9,
  image_url_list: ['https://example.com/image1.jpg', 'https://example.com/image2.jpg', 'https://example.com/image3.jpg']
}
```

## Qwen Image 2 Pro (Text-to-Image)

Uses the same parameters as Qwen Image 2, with `model_name` set to `qwen-image-2.0-pro` for enhanced output quality.

### Example Request

```javascript
const response = await fetch('https://api.flaq.ai/api/v1/image/task', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model_name: 'qwen-image-2.0-pro',
    prompt: 'A serene mountain landscape at sunset',
    width: 16,
    height: 9
  })
});

const { data } = await response.json();
const taskId = data.task_id;
```

## Qwen Image 2 Pro Edit (Image Editing)

Uses the same parameters as Qwen Image 2 Edit, with `model_name` set to `qwen-image-2.0-pro-edit` for enhanced output quality.

### Example Request

```javascript
const response = await fetch('https://api.flaq.ai/api/v1/image/task', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model_name: 'qwen-image-2.0-pro-edit',
    prompt: 'Change the sky to sunset colors',
    width: 16,
    height: 9,
    image_url_list: ['https://example.com/image.jpg']
  })
});

const { data } = await response.json();
const taskId = data.task_id;
```

## Response Format

### Initial Response

All models return a `task_id` for polling:

```json
{
  "code": 0,
  "data": {
    "task_id": "{task_id}",
    "task_status": "submitted",
    "response_url": "https://api.flaq.ai/api/v1/image/{task_id}"
  },
  "message": "success"
}
```

### Polling Response

Poll `GET /api/v1/image/{taskId}` to check status:

```json
{
  "code": 0,
  "data": {
    "task_id": "{task_id}",
    "task_status": "succeed",
    "task_status_msg": null,
    "response_url": "https://api.flaq.ai/api/v1/image/{task_id}",
    "task_result": {
      "credit": 0.0997,
      "images": [
        {
          "url": "https://example.com/generated-image.jpeg"
        }
      ]
    }
  },
  "message": "success"
}
```

### Status Values

- `submitted`: Task accepted
- `processing`: Generation in progress
- `succeed`: Generation completed successfully
- `failed`: Generation failed

## Error Handling

### Common Errors

**Invalid Aspect Ratio**
```json
{
  "code": 400,
  "message": "Ratio must be one of: 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3"
}
```

**Missing Image URL (Edit Mode)**
```json
{
  "code": 400,
  "message": "image_url_list is required for edit models"
}
```

**Too Many Images (Edit Mode)**
```json
{
  "code": 400,
  "message": "image_url_list supports a maximum of 6 images"
}
```

**Unauthorized**
```json
{
  "code": 401,
  "message": "Invalid or missing API key"
}
```

## Best Practices

### Text-to-Image Tips

1. **Be Specific**: Include subject, style, lighting, and composition details in your prompt
2. **Aspect Ratio Selection**: Choose ratio based on your use case (16:9 for web banners, 9:16 for mobile, 1:1 for social media)
3. **Use Seed for Reproducibility**: Set a fixed `seed` value when you need consistent results across requests
4. **Standard vs Pro**: Use Standard for rapid iteration when output quality is the priority

### Image Editing Tips

1. **Clear Instructions**: Be specific about what to change in the prompt
2. **Multi-Image Composition**: Provide up to 6 images and describe how they should be combined
3. **Prompt Guidance**: Describe the desired outcome rather than just listing changes
4. **Image Quality**: Higher quality input images generally produce better editing results